Context engineering
Context engineering is the practice of deciding what information an AI model sees for a given task — which files, which conventions, which prior results — and in what form. It has largely replaced prompt phrasing as the thing that most affects output quality in coding tools.
Once models became competent, the failure mode stopped being misunderstood instructions and became missing information. A model cannot follow a convention nobody stated, and it cannot avoid a module it was never shown.
So the work is curation. What goes in the rules file because it always applies, what gets attached for this task, what stays out because it would crowd the window, and what the agent should find for itself rather than being handed.
What this means in practice
Practically it comes down to three habits: put durable conventions in a rules file, attach the specific files a task touches, and let the agent search for the rest. Most complaints about output quality turn out to be one of those three missing.
Prompts for the tools this applies to
Related terms
- Context window
The context window is the maximum amount of text a model can consider at once, measured in tokens and covering everything in the request: system prompt, your instructions, the files supplied, prior conversation, and the response being generated..
- Context retrieval
Context retrieval is how an AI coding tool decides which parts of your codebase to read for a given request.
- Custom instructions
Custom instructions are standing directions you give an AI tool that apply to every request rather than a single one — preferred language and framework, response style, conventions to follow.
- Codebase indexing
Codebase indexing is the process an AI editor uses to build a searchable representation of your repository, usually by splitting files into chunks and storing vector embeddings so it can retrieve code by meaning rather than exact text match..